Perner, P. (2001). Why case-based reasoning is attractive for image interpretation. In D. Aha and I Watson (Eds.) Case-Based Reasoning Research and Development. Springer-Verlag, LNAI 2080, 27--44.

@InBook{Perner2001,
  author = 	 {Perner, Petra},
  editor = 	 {Aha, David and 
                  Watson, I.},
  title = 	 {Why case-based reasoning is attractive for image interpretation},
  chapter = 	 {},
  publisher = 	 {Springer-Verlag},
  year = 	 {2001},
  key = 	 {},
  volume = 	 {},
  number = 	 {},
  series = 	 {Case-Based Reasoning Research and Development},
  type = 	 {},
  address = 	 {},
  edition = 	 {},
  month = 	 {},
  pages = 	 {27-44},
  note = 	 {},
  annote = 	 {}
}

Author of the summary: JimDavies, 2005, jim@jimdavies.org

Cite this paper for:

CBR might be able to handle the factors that influence image interpretation, such as environmental conditions, the imaging device, noise, the number of observations in the domain, and the part of the task domain. [39]

"Invariance" is a concept that is important in visual similarity but is not considered in classical notions of similarity. [33]

Image representation Similarity measures can be classified as:

• pixel (Iconic)-matrix similarity measures
• similarity measures for comparing strings
• feature-based similarity measures (numeric, symbolic, or mixed type)
• structural similarity measures.

Image segmentation requires choosing control parameters. These parameters are often set according to aggregate data, rather than the best parameters for a given image. This paper proposes a CBR approach for parameter learning. [35]

Each case in the library has an image, non-image information (which are used for case similarity) and the parameters used on it (what is transferred). This has worked well for CT image segmentation (Perner 1999).

SUMMARY is UNFINISHED (remove this line when finished)

Summary author's notes:

• none